Equipment maintenance method and device, equipment, medium and product

Abstract

The invention discloses an equipment maintenance method and device, equipment, a medium and a product. The method comprises the following steps: acquiring at least one type of equipment data of target equipment; inputting the equipment data into a pre-trained fault diagnosis model to obtain at least one fault type currently possessed by the target equipment; any fault type is used as a target fault, and a fault severity index corresponding to the target fault is determined according to the equipment data; according to the at least one fault severity index corresponding to the target equipment and the equipment data, determining an overhaul priority index of the target equipment; and overhauling the target equipment according to the overhauling priority index. According to the technical scheme provided by the embodiment of the invention, the equipment maintenance accuracy is improved, and the equipment maintenance efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an equipment maintenance method, apparatus, equipment, medium and product. Background Art

[0002] Nuclear power plants, as efficient and clean energy sources, play a vital role worldwide. However, due to the high complexity, high risks, and high technical requirements of nuclear power plants, the proper operation and maintenance of their equipment are crucial. Failure of nuclear power plant equipment can have serious impacts on the equipment itself, the safe operation of the plant, and even the surrounding environment.

[0003] Therefore, efficient and timely monitoring of nuclear power plant equipment status and fault diagnosis have become key to ensuring safe operation. Currently, even though some equipment can provide information such as fault codes, manual troubleshooting is still required to identify the fault type, resulting in low maintenance efficiency and a need for improved accuracy. Summary of the Invention

[0004] The present application provides an equipment maintenance method, apparatus, equipment, medium and product to improve the maintenance efficiency and maintenance accuracy of equipment.

[0005] According to one aspect of the present application, there is provided a method for equipment maintenance, comprising:

[0006] Obtain at least one device data of the target device;

[0007] Input the data of each device into the pre-trained fault diagnosis model to obtain at least one fault type currently present in the target device;

[0008] Take any fault type as the target fault and determine the fault severity index corresponding to the target fault based on the data of each device;

[0009] Determining a maintenance priority index of the target device based on at least one fault severity index corresponding to the target device and data of each device;

[0010] Repair target equipment according to the repair priority index.

[0011] According to another aspect of the present application, there is provided an equipment maintenance device, comprising:

[0012] A device data acquisition module, configured to acquire at least one type of device data of a target device;

[0013] A fault type determination module is used to input the data of each device into a pre-trained fault diagnosis model to obtain at least one fault type currently possessed by the target device;

[0014] The severity index determination module is used to take any fault type as a target fault and determine the fault severity index corresponding to the target fault based on the data of each device;

[0015] a priority index calculation module, configured to determine a maintenance priority index of a target device based on at least one fault severity index corresponding to the target device and data of each device;

[0016] The equipment priority maintenance module is used to repair the target equipment according to the maintenance priority index.

[0017] According to another aspect of the present application, an electronic device is provided, comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the equipment maintenance method described in any embodiment of the present application.

[0021] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the equipment maintenance method described in any embodiment of the present application when executed.

[0022] According to another aspect of the present application, a computer program product is provided, which includes a computer program. When the computer program is executed by a processor, it implements the equipment maintenance method according to any embodiment of the present application.

[0023] The technical solution of the embodiment of the present application obtains various types of equipment data of the target equipment, diagnoses different types of faults existing in the target equipment based on these data, calculates the fault severity index for each type of fault based on the equipment data, and then comprehensively calculates the maintenance priority index of the target equipment according to the different fault severity indexes of different faults on the target equipment and various types of equipment data, so as to repair different equipment in sequence. The advantage of doing so is that it can fully analyze the data of various types of equipment, take into account the abnormal conditions of the data of different equipment when the fault occurs, and comprehensively calculate the fault severity index, which can ensure that the diagnosis of the fault severity is more accurate, reduce the misjudgment rate of fault diagnosis, and help staff to carry out targeted maintenance; further, the maintenance priority index of the target equipment is calculated based on the fault severity index of different faults, which can effectively assist operation and maintenance personnel to reasonably arrange the maintenance sequence of different equipment, thereby improving the efficiency of equipment maintenance.

[0024] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0026] Figure 1 This is a flow chart of an equipment maintenance method provided according to Example 1 of the present application;

[0027] Figure 2 is a schematic diagram of the maintenance effect of the inspection equipment provided in Example 2 of the present application;

[0028] Figure 3 This is a structural diagram of an equipment maintenance device provided according to the third embodiment of the present application;

[0029] Figure 4 It is a structural diagram of an electronic device for implementing the equipment maintenance method of an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Example 1

[0033] Figure 1 A flowchart of an equipment maintenance method is provided for the first embodiment of the present application. This embodiment is applicable to the maintenance of various types of equipment in a nuclear power plant. The method can be executed by an equipment maintenance device, which can be implemented in the form of hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0034] S110: Obtain at least one device data of the target device.

[0035] Among them, the target device can be any device that needs to be repaired. In fact, this case can be applied to any electronic device in any scenario, but in order to better explain the contents described in the embodiments and implementation methods of this application, the subsequent solutions are described using the equipment in a nuclear power plant as an example. Then in a nuclear power plant, any electronic device with data processing or communication functions can be used as a target device for networked fault diagnosis. The device data can be any data collected from the target device, such as relevant data generated by the device during operation. Taking the equipment in a nuclear power plant as an example, it can include but is not limited to the working data of the nuclear power plant equipment, energy consumption and production capacity data, and appearance data obtained by photographing the appearance of these devices.

[0036] Exemplarily, the working data include but are not limited to temperature data types: coolant temperature, steam temperature, reactor core temperature; pressure data types: coolant pressure, reactor pressure, steam generator pressure; flow data types: coolant flow, steam flow, fuel rod flow; radiation data types: air radiation dose rate, discharge water radiation dose rate, etc.;

[0037] Energy consumption and production capacity data include but are not limited to the following types: power consumption, power output, operating current value, operating voltage value, etc.;

[0038] Appearance data includes but is not limited to the following types: number of damaged locations, number of corroded locations, damaged area, corroded area, etc.

[0039] Of course, the various types of device data here are only examples and are not exhaustive.

[0040] S120: Input the data of each device into a pre-trained fault diagnosis model to obtain at least one fault type currently possessed by the target device.

[0041] Among them, the fault diagnosis model is used to judge what kind of fault has occurred in the target device based on various types of device data. The basic model of the fault diagnosis model can be any machine learning model, such as a neural network model, etc., and the embodiments of the present application do not limit this. The basic model is trained through a large amount of pre-labeled device data to obtain a fault diagnosis model with fault diagnosis capabilities. The model inputs various types of device data of the target device, and the model outputs the diagnosed fault type, and can output multiple fault types. It is understandable that the target device may have multiple different types of faults at the same time. The training process of the machine learning model can adopt any model training method in the relevant technology, and the present application does not limit it here.

[0042] S130 . Taking any fault type as a target fault, and determining a fault severity index corresponding to the target fault based on data of each device.

[0043] It is understandable that any equipment failure needs to be repaired, so each type of failure must be analyzed separately. The target failure can be any type of failure generated by the target device, and further analysis is performed on the target failure. It is conceivable that any failure will be reflected in the changes in the device data, so based on the various device data, the severity of the target failure is evaluated. Accordingly, the fault severity index can be used to characterize the severity of the target fault (any type of failure in the target device). It can be a data indicator. For example, the value of the fault severity index can be calculated based on the values of various device data, and the severity of different fault types can be distinguished based on the size of the value. It is understandable that the larger the value of the fault severity index, the more serious the fault.

[0044] For example, the duration of the target fault, the degree of abnormality in the device data, and the number of other devices affected by the target fault can be used as the basis for calculating the fault severity index. Of course, another machine learning model can also be pre-trained, and the device data related to the target fault can be input into the model to cause the model to output the numerical value of the fault severity index of the target fault. This embodiment of the present application is not limited here.

[0045] S140: Determine a maintenance priority index of the target device according to at least one fault severity index corresponding to the target device and data of each device.

[0046] As mentioned earlier, a device can have multiple faults, each of which can be assigned a fault severity index. The repair priority index can be used to characterize the priority level of repair for a target device. It can also be a data indicator. For example, a repair priority index can be calculated based on the fault severity index values corresponding to various faults in the target device, along with different device data. This value can then be used to differentiate the repair priorities of different devices.

[0047] For example, the weighted sum of the values of the fault severity indicators corresponding to different faults can be calculated, and the product of the impact factors caused by the various types of data on the abnormality of the target device (such as the value of the impact degree, which can be pre-defined according to different equipment data) can be calculated to obtain the value of the maintenance priority indicator. Of course, another machine learning model can also be pre-trained, and the equipment data related to the target device and the values of the fault severity indicators corresponding to different faults can be input into the model, so that the model outputs the value of the maintenance priority indicator of the target device. This is not limited to the embodiments of the present application.

[0048] S150: Repair the target equipment according to the repair priority index.

[0049] It is understood that in a specific environment (such as the nuclear power plant shown in the previous example), there may be multiple devices. Each device can calculate a corresponding maintenance priority index. The values of the maintenance priority index are compared to arrange the maintenance of these devices in order. It is understood that the larger the value of the maintenance priority index, the higher the maintenance priority.

[0050] The technical solution of the embodiment of the present application obtains various types of equipment data of the target equipment, diagnoses different types of faults existing in the target equipment based on these data, calculates the fault severity index for each type of fault based on the equipment data, and then comprehensively calculates the maintenance priority index of the target equipment according to the different fault severity indexes of different faults on the target equipment and various types of equipment data, so as to repair different equipment in sequence. The advantage of doing so is that it can fully analyze the data of various types of equipment, take into account the abnormal conditions of the data of different equipment when the fault occurs, and comprehensively calculate the fault severity index, which can ensure that the diagnosis of the fault severity is more accurate, reduce the misjudgment rate of fault diagnosis, and help staff to carry out targeted maintenance; further, the maintenance priority index of the target equipment is calculated based on the fault severity index of different faults, which can effectively assist operation and maintenance personnel to reasonably arrange the maintenance sequence of different equipment, thereby improving the efficiency of equipment maintenance.

[0051] In an optional implementation, determining the fault severity index corresponding to the target fault based on the data of each device in S130 may include:

[0052] S131 . Determine, based on a preset data threshold, a target ratio of the number of types of abnormal data that do not meet the data threshold in the data of each device to the number of types of data affected by the fault.

[0053] Among them, the data threshold can be the basis for judging whether the device data conforms to the normal state. It can be understood that each type of device data corresponds to its own data threshold. When the value of the device data does not conform to the range specified by the data threshold, the device data can be considered to be in an abnormal state. At this time, the device data that does not conform to the data threshold is regarded as abnormal data. The number of types of abnormal data corresponds to the number of abnormal device data. The number of types of fault-affected data can be the number of types of device data that may be affected by the target fault. It should be noted that a certain fault generated by the target device does not necessarily affect all the device data of the target device, and when a fault occurs, the affected device data may not necessarily show abnormalities. Therefore, only the device data that can be affected by the target fault is discussed. It can be understood that the target ratio is the ratio of the number of types of abnormal data corresponding to the target fault to the number of types of fault-affected data, that is, the proportion.

[0054] In other words, first determine the number of abnormal data in the device data corresponding to the target fault (or, in other words, the device data that the target fault may affect), and then calculate the proportion of abnormal data to the number of types of fault-affecting data corresponding to the target fault. This target proportion can, to a certain extent, reflect the extent of the negative impact of the target fault on the target device.

[0055] S132: For any abnormal data, determine the degree to which the value of the abnormal data exceeds the corresponding data threshold.

[0056] For any device data potentially affected by the target fault, if an anomaly occurs, the magnitude relationship between the device data and its corresponding data threshold is used to calculate the degree to which the device data does not meet the data threshold, i.e., the degree of exceedance. This degree of exceedance can reflect the degree of anomaly in the device output. This degree of exceedance can be calculated as a difference or a ratio, which is not limited in this embodiment of the present application.

[0057] S133: Determine the number of associated devices corresponding to the target fault and the estimated repair time of the target fault.

[0058] The associated devices corresponding to a target fault can include the target device itself, as well as other devices potentially affected by the target fault, such as other devices in processes preceding or following the target device, or in the same system. Accordingly, the number of associated devices is the number of associated devices affected by the target fault. For example, in a nuclear power plant, if the fault type is an abnormal cooling capacity of the cooling system, which causes a temperature rise in the reactor, the associated devices in this case are the cooling system and the reactor, so the number of associated devices is 2. If the fault type is insufficient power supply, the number of associated devices is the total number of devices supplied by the power supply.

[0059] The estimated repair time of the target fault may be the time required to repair the fault type of the target fault. The preset repair time may be an average of the time taken in historical maintenance records.

[0060] S134. Determine a fault severity index based on the target ratio, the degree of exceedance, the number of associated devices, and the estimated repair time.

[0061] The target ratio, degree of excess, number of associated devices, and estimated repair time determined in the aforementioned steps are calculated using a preset method, such as multiplying the target ratio, degree of excess, number of associated devices, and estimated repair time, and the resulting calculation result is used as the fault severity indicator. Of course, this preset method can be determined by relevant technicians based on extensive testing or experience.

[0062] In a further optional embodiment, the degree of excess may be determined by:

[0063] If the value of the device data is greater than the upper limit of the data threshold, the ratio of the value of the device data to the upper limit is used as the degree of excess;

[0064] If the value of the device data is less than the lower limit of the data threshold, the ratio of the lower limit to the value of the device data is used as the degree of excess;

[0065] If the value of the device data is less than or equal to the upper limit of the data threshold and greater than or equal to the lower limit of the data threshold, the degree of excess is zero.

[0066] It is understood that if the value of device data exceeds the corresponding data threshold, that is, the value of the device data is greater than the upper limit of the data threshold or less than the lower limit of the data threshold, then the device data is actually abnormal data. If the value of device data does not exceed the corresponding data threshold, that is, the value of the device data is less than or equal to the upper limit of the data threshold and greater than or equal to the lower limit of the data threshold, then the device data can be considered to be normal data (of course, as mentioned above, device data affected by a fault may or may not be abnormal).

[0067] When the device data value exceeds the upper threshold, the ratio of the device data value to the upper threshold is calculated, and the result is used as the degree of excess. When the device data value is less than the lower threshold, the ratio of the lower threshold to the device data value is calculated, and the result is used as the degree of excess. Furthermore, when the device data value is less than or equal to the upper threshold and greater than or equal to the lower threshold, the degree of excess is zero, indicating that the device data is normal.

[0068] In a practical example, the fault severity index of the target fault can be calculated according to the following formula:

[0069]

[0070]

[0071] Among them, GZZB is the fault severity index, NUM is the number of types of data used to identify the fault (that is, the number of types of device data that may be affected by the target fault mentioned above), num is the number of types of abnormal data mentioned above, and over i (t) is the excess degree parameter (the aforementioned excess degree value) corresponding to the i-th abnormal data that exceeds its corresponding data threshold, can i (t) is the value of the i-th abnormal data, T is the detection time of a detection cycle, t iis the duration that the i-th abnormal data exceeds its corresponding data threshold in the detection cycle, CAN imax is the upper limit of the data threshold corresponding to the i-th abnormal data, CAN imin is the lower limit of the data threshold corresponding to the i-th abnormal data, jst is the estimated time required to repair the fault, and p is the number of associated devices of the fault.

[0072] The above two implementation methods provide a practical solution for how to calculate the fault severity index. They comprehensively consider the proportion of abnormal data related to the target fault, the degree of excess of data anomalies, the number of associated devices of the fault and the estimated repair time of the fault due to strong winds, and then calculate a quantitative fault severity index that can be used for direct reference, which improves the comprehensiveness, rationality and accuracy of fault severity diagnosis, and helps to improve the accuracy and efficiency of equipment maintenance.

[0073] In another optional embodiment, the method may include: obtaining the number of maintenance times of the target device from the time the target device is put into use to the current time, and the number of days that have passed since the last maintenance of the target device to the current time;

[0074] Correspondingly, the method of determining the maintenance priority index of the target device based on at least one fault severity index corresponding to the target device and the data of each device in S140 may include: calculating the total severity parameter of the target device based on the fault severity index corresponding to each fault type; and determining the maintenance priority index based on the number of maintenance times and the number of days experienced, as well as the total severity parameter.

[0075] The total severity parameter may be a comprehensive indicator of the severity of all faults occurring in the target device. The fault severity indicators of different faults may be directly accumulated, or weighted and calculated to obtain the total severity parameter as a quantitative reference standard.

[0076] Then, according to a preset calculation method, the total severity parameter, the number of maintenance times, and the number of days elapsed are calculated, and the calculated result is used as the maintenance priority index. For example, the product of the total severity parameter, the number of maintenance times, the number of days elapsed, etc. can be used as the maintenance priority index.

[0077] In a further optional implementation, calculating the total severity parameter of the target device based on the fault severity index corresponding to each fault type may include:

[0078] For any target fault, the product of the estimated repair time required for the target fault, the total labor cost of the personnel responsible for the target equipment, the unit power production per hour of the nuclear power plant where the target equipment is located, the preset weight corresponding to the target fault, and the fault severity index corresponding to the target fault is used as the severity parameter of the target fault; for each fault type of the target equipment, the sum of the severity parameters is used as the total severity parameter.

[0079] Among them, the severity parameter can be the calculation reference data corresponding to a single fault, and accordingly, the total severity parameter can be the sum of the severity parameters of all faults. It should be noted that once a device fails, maintenance personnel are required to repair it. At the same time, the failure of the device causes the nuclear power plant to be unable to generate electricity normally. At this time, the nuclear power plant staff responsible for the device cannot work normally. It is necessary to consider both the labor expenses of the staff and the situation where the nuclear power plant cannot produce electricity. Therefore, the sum of the total labor cost and the unit production electricity is used as one of the reference quantities. The estimated repair time, the sum of the total labor cost and the unit production electricity, the different preset weights corresponding to different faults, and the fault severity index corresponding to different faults are multiplied to obtain a severity parameter for each fault. These severity parameters corresponding to all faults of the target device are then accumulated to obtain the total severity parameter. Of course, the preset weight can be set by relevant technical personnel based on a large number of experiments or manual experience, and the embodiments of this application are not limited to this.

[0080] Taking the above two implementations as an example, the maintenance priority index of the target equipment in the nuclear power plant can be calculated according to the following formula:

[0081]

[0082] Among them, YXZB is the maintenance priority index, time is the total number of maintenance times from the time the equipment was put into use to the current time, day is the number of days from the last inspection to the current date, J is the total number of fault types detected by the equipment, GZZB j is the fault severity index of the jth fault detected by the equipment, k j jst is the preset weight of the jth fault detected by the device, j is the estimated time required for the equipment to repair the jth fault, E is the amount of electricity produced by the nuclear power plant per hour, YN is the number of workers responsible for operating or monitoring the equipment, and EYN is the hourly labor cost of the workers responsible for operating or monitoring the equipment.

[0083] Equipment maintenance is performed by specialized maintenance technicians, and equipment operation is performed by general staff. During the equipment maintenance process, general staff cannot operate the equipment and can only perform some trivial tasks, which is equivalent to being idle. Human resources will be wasted. By considering the time required for maintenance and employee fees, it is helpful to take human resources into account in the priority of equipment maintenance. Equipment that wastes more human resources during the maintenance process will be more likely to be given priority for maintenance, thereby reducing the degree of human resource waste.

[0084] The preset weights can be pre-set by those skilled in the art between 1 and 5 based on the impact of different fault types on different equipment. The greater the impact, the greater the weight. For example, for a nuclear reactor vessel, the focus is on ensuring the safe conduct of the nuclear reaction, followed by temperature control. Therefore, the weight of faults related to nuclear leakage or nuclear radiation can be set to 5, the weight of faults related to temperature can be set to 3-4, and the weight of faults related to energy consumption can be set to 1. For another example, for a steam turbine, the focus is on generating electricity through steam. Therefore, the weight of faults related to energy consumption and production capacity can be set to 5, and the rest can be set between 1 and 2. Of course, these weighting methods are merely examples and should not be understood as limiting this solution.

[0085] The above two implementations provide a practical solution for how to calculate the maintenance priority index, which comprehensively considers the number of maintenance times, fault severity index, fault weight, staff loss of work, and unavailability of output, and then calculates a quantitative maintenance priority index that can be used for direct reference, thereby improving the comprehensiveness, rationality and accuracy of fault severity diagnosis, and helping to improve the accuracy and efficiency of equipment maintenance.

[0086] Example 2

[0087] Figure 2 This is a schematic diagram of the inspection equipment maintenance effect provided in the second embodiment of this application. This embodiment of the application is based on the above embodiments and implementation methods, and supplements how to inspect the maintenance effect of the target equipment after maintenance. Figure 2 As shown, the method includes:

[0088] S210: Obtain at least one operating data of the target device within a preset time period after maintenance.

[0089] The operating data is essentially the same as the device data in the aforementioned embodiments. However, the term "operating data" is used here to distinguish it from the device data in the aforementioned embodiments. In this embodiment, operating data refers to various data detected by the target device within a period of time after the maintenance is completed. The preset time period can be set by relevant technicians based on experience, for example, one week, and is not limited in this embodiment.

[0090] S220: Input each operating data into a fault diagnosis model to obtain a post-repair fault type generated by the target device after maintenance.

[0091] The fault diagnosis model is the same as the fault diagnosis model in the above embodiment. In this embodiment, the post-repair fault type refers to the fault type diagnosed after the target device has been repaired.

[0092] S230: Determine, based on the post-repair fault type and the operating data, the target number of times the operating data corresponding to each post-repair fault type fails to meet the data threshold within a preset time period, and the abnormal duration of the failure.

[0093] The data threshold is the same as that in the previous embodiment, and the target number can be the number of abnormalities in the operating data that may be affected by the type of fault after repair within a preset time period. The abnormal duration that does not meet the data threshold can be the duration of the abnormality in the operating data.

[0094] Of course, the target number and the abnormal duration can be obtained by monitoring the operating data corresponding to the post-repair fault type.

[0095] S240: Determine the maintenance effect index of the target equipment according to the target number of times, abnormal duration, and preset fault weight corresponding to each post-repair fault type.

[0096] Among them, the maintenance effect index can be used to characterize the actual working or production capacity of the target equipment after maintenance, that is, it reflects the effect of the repair and can be a quantitative indicator parameter.

[0097] For example, the target number of times corresponding to each post-repair fault type is combined with the abnormal duration, and a weighted sum is calculated based on a preset fault weight, which can be used as a maintenance effect indicator.

[0098] S250: In response to the number of times that the maintenance effect index is greater than the preset effect index threshold meeting the preset consecutive number, determining that the target device has a replacement requirement.

[0099] The effect index threshold can be the basis for judging whether the maintenance effect meets the standard. It is set by relevant technical personnel based on a large number of tests or manual experience. For example, it can be set between 0 and 1. The maintenance effect threshold can represent the tolerance of the nuclear power plant to old equipment. The larger the upper limit of the threshold, the higher the tolerance. It can be understood that the smaller the value of the maintenance effect index, the better the maintenance effect. When the maintenance effect index is greater than the effect index threshold too many times, for example, two or three times in a row, it is considered that the target equipment is still unable to undertake production tasks normally even after repairs, then it is determined that the target equipment has a replacement need, that is, it is necessary to purchase new equipment to replace the target equipment. Of course, the preset consecutive times are also set in advance by relevant technical personnel, and the embodiments of the present application do not limit this.

[0100] Based on the above content, the embodiment of the present application further provides a specific example, and the maintenance effect index can be calculated by the following formula:

[0101]

[0102] Among them, XGZB is the maintenance effect index, M is the number of fault types detected after the equipment maintenance, k m is the preset weight of the mth fault detected after equipment maintenance, X m is the number of data types involved in identifying the fault type of the mth fault detected after equipment maintenance, time mx TIME is the number of times that the xth type of data involved in identifying the fault type of the mth fault detected after equipment maintenance exceeds its corresponding data threshold within a week. mx The total duration that the xth type of data involved in identifying the fault type of the mth fault detected after equipment maintenance exceeds its corresponding data threshold within one week.

[0103] The technical solution of the embodiment of the present application provides a practical solution for determining the maintenance effect index of the target equipment that has been repaired. The maintenance effect index is used to judge the effectiveness of the maintenance personnel's maintenance of the equipment, and the effect index threshold is set to determine whether the equipment needs to be replaced. This is conducive to timely replacement of old equipment or equipment with severe damage, and avoids excessive repeated maintenance of old equipment.

[0104] Example 3

[0105] Figure 3 This is a schematic diagram of the structure of an equipment maintenance device provided in Example 3 of this application. Figure 3 As shown, the device 300 includes:

[0106] A device data acquisition module 310 is configured to acquire at least one type of device data of a target device;

[0107] The fault type determination module 320 is used to input the data of each device into a pre-trained fault diagnosis model to obtain at least one fault type currently present in the target device;

[0108] The severity index determination module 330 is used to take any fault type as a target fault and determine the fault severity index corresponding to the target fault based on the data of each device;

[0109] A priority index calculation module 340 is used to determine a maintenance priority index of a target device based on at least one fault severity index corresponding to the target device and data of each device;

[0110] The equipment priority maintenance module 350 is used to perform maintenance on the target equipment according to the maintenance priority index.

[0111] The technical solution of the embodiment of the present application obtains various types of equipment data of the target equipment, diagnoses different types of faults existing in the target equipment based on these data, calculates the fault severity index for each type of fault based on the equipment data, and then comprehensively calculates the maintenance priority index of the target equipment according to the different fault severity indexes of different faults on the target equipment and various types of equipment data, so as to repair different equipment in sequence. The advantage of doing so is that it can fully analyze the data of various types of equipment, take into account the abnormal conditions of the data of different equipment when the fault occurs, and comprehensively calculate the fault severity index, which can ensure that the diagnosis of the fault severity is more accurate, reduce the misjudgment rate of fault diagnosis, and help staff to carry out targeted maintenance; further, the maintenance priority index of the target equipment is calculated based on the fault severity index of different faults, which can effectively assist operation and maintenance personnel to reasonably arrange the maintenance sequence of different equipment, thereby improving the efficiency of equipment maintenance.

[0112] In an optional implementation, the severity indicator determination module 330 may include:

[0113] A ratio determination unit is used to determine, based on a preset data threshold, a target ratio of the number of types of abnormal data that do not meet the data threshold in the data of each device to the number of types of data affected by the fault;

[0114] an excess degree determining unit, configured to determine, for any abnormal data, an excess degree by which the value of the abnormal data exceeds a corresponding data threshold;

[0115] A device number determination unit, used to determine the number of associated devices corresponding to a target fault and the estimated repair time of the target fault;

[0116] The severity index determination unit is used to determine the fault severity index based on the target ratio, the degree of exceedance, the number of related devices and the estimated repair time.

[0117] In an optional implementation manner, the exceeding degree determining unit includes:

[0118] a first exceeding degree determining subunit, configured to use, if the value of the device data is greater than an upper limit of the data threshold, a ratio of the value of the device data to the upper limit as the exceeding degree;

[0119] a second exceeding degree determining subunit, configured to, if the value of the device data is less than a lower limit of the data threshold, use a ratio of the lower limit to the value of the device data as the exceeding degree;

[0120] The third exceeding degree determining subunit is configured to determine that the exceeding degree is zero if the value of the device data is less than or equal to the upper limit of the data threshold and greater than or equal to the lower limit of the data threshold.

[0121] In an optional implementation, the apparatus 300 may further include:

[0122] The device information acquisition unit is used to obtain the number of maintenance times of the target device from the time it was put into use to the current time, and the number of days that have passed since the last maintenance of the target device to the current time;

[0123] Accordingly, the priority index calculation module 340 may include:

[0124] A total severity parameter determination unit, configured to calculate a total severity parameter of a target device based on the fault severity index corresponding to each fault type;

[0125] The priority index determination unit is used to determine the maintenance priority index according to the number of maintenance times and the number of days experienced, as well as the total severity parameter.

[0126] In an optional implementation manner, the total severity parameter determination unit may include:

[0127] a severity parameter determination subunit, for any target fault, taking the product of the estimated repair time required for the target fault, the total labor cost of the personnel responsible for the target equipment, the hourly unit power production of the nuclear power plant where the target equipment is located, a preset weight corresponding to the target fault, and the fault severity index corresponding to the target fault as the severity parameter of the target fault;

[0128] The total severity parameter determination subunit is configured to take the sum of the severity parameters of each fault type of the target device as the total severity parameter.

[0129] In an optional implementation, the apparatus 300 may further include:

[0130] An operation data acquisition module, used to acquire at least one type of operation data of the target equipment within a preset time period after maintenance;

[0131] A post-repair fault determination module is used to input various operating data into the fault diagnosis model to obtain the post-repair fault type generated by the target equipment after maintenance;

[0132] A number and duration determination module is used to determine, based on the post-repair fault type and the operating data, a target number of times that the operating data corresponding to each post-repair fault type does not meet the data threshold within a preset time period, and an abnormal duration that does not meet the data threshold;

[0133] The maintenance effect index determination module is used to determine the maintenance effect index of the target equipment based on the target number of fault types after repair, the abnormal duration and the preset fault weight;

[0134] The equipment replacement demand determination module is used to determine that the target equipment has a replacement demand in response to the number of times that the maintenance effect index is greater than a preset effect index threshold meeting a preset continuous number of times.

[0135] The equipment maintenance device provided in the embodiments of the present application can execute the equipment maintenance method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects for executing each equipment maintenance method.

[0136] Example 4

[0137] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0138] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0139] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0140] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the equipment maintenance method.

[0141] In some embodiments, the device servicing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the device servicing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to execute the device servicing method in any other appropriate manner (e.g., by means of firmware).

[0142] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0143] Computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0144] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0145] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0146] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0147] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0148] The present application also discloses a computer program product, comprising a computer program that, when executed by a processor, implements the device maintenance method provided in any of the embodiments of the present application. This program product and the device maintenance method disclosed in each embodiment of the present application share the same inventive concept and are therefore not described in detail here.

[0149] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of this application can be achieved. This is not limited herein.

[0150] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A method for equipment maintenance, characterized in that: include: Obtain at least one device data of the target device; Inputting the data of each device into a pre-trained fault diagnosis model to obtain at least one fault type currently possessed by the target device; Taking any one of the fault types as a target fault, and determining a fault severity index corresponding to the target fault based on the device data; determining a maintenance priority index of the target device according to at least one fault severity index corresponding to the target device and each of the device data; The target device is repaired according to the repair priority indicator.

2. The method according to claim 1, characterized in that Determining the fault severity index corresponding to the target fault based on the device data includes: According to a preset data threshold, determining a target ratio of the number of types of abnormal data that do not meet the data threshold in the data of each device to the number of types of data affected by the fault; For any of the abnormal data, determining the degree to which the value of the abnormal data exceeds the corresponding data threshold; Determine the number of associated devices corresponding to the target fault and the estimated repair time of the target fault; The fault severity index is determined according to the target ratio, the degree of excess, the number of associated devices, and the estimated repair time.

3. The method according to claim 2, characterized in that The degree of excess is determined as follows: If the value of the device data is greater than the upper limit of the data threshold, the ratio of the value of the device data to the upper limit is used as the degree of excess; If the value of the device data is less than the lower limit of the data threshold, the ratio of the lower limit to the value of the device data is used as the degree of excess; If the value of the device data is less than or equal to the upper limit of the data threshold and greater than or equal to the lower limit of the data threshold, the degree of excess is zero.

4. The method according to claim 1, wherein The method comprises: Obtain the number of maintenance times of the target device from the time it was put into use to the current time, and the number of days that have passed since the last maintenance of the target device to the current time; Determining the maintenance priority index of the target device according to the at least one fault severity index corresponding to the target device and each device data includes: Calculating a total severity parameter of the target device according to the fault severity index corresponding to each fault type; The maintenance priority index is determined according to the number of maintenance times, the number of days experienced, and the total severity parameter.

5. The method according to claim 4, characterized in that Calculating the total severity parameter of the target device according to the fault severity index corresponding to each fault type includes: For any target fault, the product of the estimated repair time required for the target fault, the total labor cost of the personnel responsible for the target equipment, the unit power production per hour of the nuclear power plant where the target equipment is located, the preset weight corresponding to the target fault, and the fault severity index corresponding to the target fault is used as the severity parameter of the target fault; For each fault type of the target device, the sum of the severity parameters is used as the total severity parameter.

6. The method according to any one of claims 1 to 5, characterized in that After the target device is repaired, the method includes: Acquiring at least one operating data of the target device within a preset time period after maintenance; Inputting each of the operating data into the fault diagnosis model to obtain the post-repair fault type generated by the target device after maintenance; Determining, based on the post-repair fault type and the operating data, a target number of times that the operating data corresponding to each post-repair fault type does not meet the data threshold within the preset time period, and an abnormal duration of not meeting the data threshold; Determine the maintenance effect index of the target equipment according to the target number of times, the abnormal duration and the preset fault weight corresponding to each post-repair fault type; In response to the number of times that the maintenance effect index is greater than the preset effect index threshold meeting the preset consecutive number, it is determined that the target device has a replacement requirement.

7. An equipment maintenance device, characterized in that: include: A device data acquisition module, configured to acquire at least one type of device data of a target device; A fault type determination module is used to input the data of each device into a pre-trained fault diagnosis model to obtain at least one fault type currently possessed by the target device; a severity index determination module, configured to take any of the fault types as a target fault and determine a fault severity index corresponding to the target fault based on the device data; a priority index calculation module, configured to determine a maintenance priority index of the target device based on at least one fault severity index corresponding to the target device and each of the device data; The equipment priority maintenance module is used to repair the target equipment according to the maintenance priority index.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the equipment maintenance method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the equipment maintenance method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the equipment maintenance method according to any one of claims 1 to 6.

Images